{ "info": { "_postman_id": "993e952b-b257-41fd-9a75-3ee50cf85726", "name": "Cerebras Inference Chat API", "description": "Generate conversational responses using a structured message format with roles (system, user, assistant, developer, tool). Best for chatbots, assistants, and multi-turn conversations.\n", "schema": "https://schema.getpostman.com/json/collection/v2.1.0/collection.json", "createdAt": "2026-07-28T01:18:42.000Z", "updatedAt": "2026-07-28T01:18:42.000Z", "lastUpdatedBy": "35240", "uid": "35240-993e952b-b257-41fd-9a75-3ee50cf85726" }, "item": [ { "name": "v1", "item": [ { "name": "chat", "item": [ { "name": "completions", "item": [ { "name": "Create chat completion", "id": "57ee2b5e-bb80-4e45-b44c-8a9277f6cab8", "protocolProfileBehavior": { "disableBodyPruning": true }, "request": { "method": "POST", "header": [ { "description": "The compression encoding applied to the request body. When set, the request body must be gzip-compressed. Can be combined with any supported `Content-Type`. Supported values: `gzip`.\n", "key": "Content-Encoding", "value": "gzip" }, { "description": "Controls the queue time threshold for requests using the `flex` or `auto` service tiers. Requests are preemptively rejected if the rolling average queue time exceeds this threshold. Valid range: `50`\u2013`20000` (milliseconds). **Private Preview.**\n", "key": "queue_threshold", "value": "" }, { "key": "Content-Type", "value": "application/json" }, { "key": "Accept", "value": "application/json" } ], "body": { "mode": "raw", "raw": "{\n \"model\": \"\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"\",\n \"name\": \"\"\n },\n {\n \"role\": \"system\",\n \"content\": \"\",\n \"name\": \"\"\n }\n ],\n \"clear_thinking\": \"\",\n \"frequency_penalty\": 0,\n \"logit_bias\": null,\n \"logprobs\": false,\n \"max_completion_tokens\": \"\",\n \"parallel_tool_calls\": true,\n \"prediction\": {\n \"type\": \"content\",\n \"content\": \"\"\n },\n \"presence_penalty\": 0,\n \"prompt_cache_key\": null,\n \"reasoning_effort\": \"high\",\n \"response_format\": {\n \"type\": \"text\"\n },\n \"seed\": \"\",\n \"service_tier\": \"default\",\n \"stop\": \"\",\n \"stream\": \"\",\n \"temperature\": \"\",\n \"tool_choice\": \"auto\",\n \"tools\": [\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"\",\n \"description\": \"\",\n \"parameters\": {}\n }\n },\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"\",\n \"description\": \"\",\n \"parameters\": {}\n }\n }\n ],\n \"top_logprobs\": \"\",\n \"top_p\": \"\",\n \"user\": \"\"\n}", "options": { "raw": { "headerFamily": "json", "language": "json" } } }, "url": { "raw": "{{baseUrl}}/v1/chat/completions", "host": [ "{{baseUrl}}" ], "path": [ "v1", "chat", "completions" ] }, "description": "Generate conversational responses using a structured message format with roles (system, user, assistant, developer, tool). Best for chatbots, assistants, and multi-turn conversations.\n" }, "response": [ { "id": "11946320-bc0a-4906-8513-22f5f03b8a79", "name": "Successful response", "originalRequest": { "method": "POST", "header": [ { "description": "The compression encoding applied to the request body. When set, the request body must be gzip-compressed. Can be combined with any supported `Content-Type`. Supported values: `gzip`.\n", "key": "Content-Encoding", "value": "gzip" }, { "description": "Controls the queue time threshold for requests using the `flex` or `auto` service tiers. Requests are preemptively rejected if the rolling average queue time exceeds this threshold. Valid range: `50`\u2013`20000` (milliseconds). **Private Preview.**\n", "key": "queue_threshold", "value": "" }, { "key": "Content-Type", "value": "application/json" }, { "key": "Accept", "value": "application/json" }, { "description": "Added as a part of security scheme: bearer", "key": "Authorization", "value": "Bearer " } ], "body": { "mode": "raw", "raw": "{\n \"model\": \"\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"\",\n \"name\": \"\"\n },\n {\n \"role\": \"system\",\n \"content\": \"\",\n \"name\": \"\"\n }\n ],\n \"clear_thinking\": \"\",\n \"frequency_penalty\": 0,\n \"logit_bias\": null,\n \"logprobs\": false,\n \"max_completion_tokens\": \"\",\n \"parallel_tool_calls\": true,\n \"prediction\": {\n \"type\": \"content\",\n \"content\": \"\"\n },\n \"presence_penalty\": 0,\n \"prompt_cache_key\": null,\n \"reasoning_effort\": \"high\",\n \"response_format\": {\n \"type\": \"text\"\n },\n \"seed\": \"\",\n \"service_tier\": \"default\",\n \"stop\": \"\",\n \"stream\": \"\",\n \"temperature\": \"\",\n \"tool_choice\": \"auto\",\n \"tools\": [\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"\",\n \"description\": \"\",\n \"parameters\": {}\n }\n },\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"\",\n \"description\": \"\",\n \"parameters\": {}\n }\n }\n ],\n \"top_logprobs\": \"\",\n \"top_p\": \"\",\n \"user\": \"\"\n}", "options": { "raw": { "headerFamily": "json", "language": "json" } } }, "url": { "raw": "{{baseUrl}}/v1/chat/completions", "host": [ "{{baseUrl}}" ], "path": [ "v1", "chat", "completions" ] } }, "status": "OK", "code": 200, "_postman_previewlanguage": "json", "header": [ { "key": "Content-Type", "value": "application/json" } ], "cookie": [], "responseTime": null, "body": "{\n \"id\": \"\",\n \"choices\": [\n {\n \"finish_reason\": \"stop\",\n \"index\": \"\",\n \"logprobs\": {},\n \"reasoning_logprobs\": {},\n \"message\": {\n \"content\": \"\",\n \"role\": \"\",\n \"reasoning\": \"\",\n \"tool_calls\": [\n {\n \"id\": \"\",\n \"type\": \"function\",\n \"function\": {\n \"name\": \"\",\n \"arguments\": \"\"\n }\n },\n {\n \"id\": \"\",\n \"type\": \"function\",\n \"function\": {\n \"name\": \"\",\n \"arguments\": \"\"\n }\n }\n ]\n }\n },\n {\n \"finish_reason\": \"length\",\n \"index\": \"\",\n \"logprobs\": {},\n \"reasoning_logprobs\": {},\n \"message\": {\n \"content\": \"\",\n \"role\": \"\",\n \"reasoning\": \"\",\n \"tool_calls\": [\n {\n \"id\": \"\",\n \"type\": \"function\",\n \"function\": {\n \"name\": \"\",\n \"arguments\": \"\"\n }\n },\n {\n \"id\": \"\",\n \"type\": \"function\",\n \"function\": {\n \"name\": \"\",\n \"arguments\": \"\"\n }\n }\n ]\n }\n }\n ],\n \"created\": \"\",\n \"model\": \"\",\n \"object\": \"chat.completion\",\n \"system_fingerprint\": \"\",\n \"service_tier\": \"\",\n \"service_tier_used\": \"default\",\n \"usage\": {\n \"prompt_tokens\": \"\",\n \"completion_tokens\": \"\",\n \"total_tokens\": \"\",\n \"image_tokens\": \"\",\n \"prompt_tokens_details\": {\n \"cached_tokens\": \"\"\n },\n \"completion_tokens_details\": {\n \"accepted_prediction_tokens\": \"\",\n \"rejected_prediction_tokens\": \"\",\n \"reasoning_tokens\": \"\"\n }\n },\n \"time_info\": {\n \"queue_time\": \"\",\n \"prompt_time\": \"\",\n \"completion_time\": \"\",\n \"total_time\": \"\",\n \"created\": \"\"\n }\n}", "createdAt": "2026-07-28T01:18:43.000Z", "updatedAt": "2026-07-28T01:18:43.000Z", "uid": "35240-11946320-bc0a-4906-8513-22f5f03b8a79" } ], "createdAt": "2026-07-28T01:18:43.000Z", "updatedAt": "2026-07-28T01:18:43.000Z", "uid": "35240-57ee2b5e-bb80-4e45-b44c-8a9277f6cab8" } ], "id": "34e66681-50ee-450c-9386-b602cbcdd94e", "createdAt": "2026-07-28T01:18:43.000Z", "updatedAt": "2026-07-28T01:18:43.000Z", "uid": "35240-34e66681-50ee-450c-9386-b602cbcdd94e" } ], "id": "a24f5dc3-a09b-48ed-90d7-f5c40d1165d6", "createdAt": "2026-07-28T01:18:43.000Z", "updatedAt": "2026-07-28T01:18:43.000Z", "uid": "35240-a24f5dc3-a09b-48ed-90d7-f5c40d1165d6" } ], "id": "cf02c590-7ab0-4189-a461-b27020a7e472", "createdAt": "2026-07-28T01:18:43.000Z", "updatedAt": "2026-07-28T01:18:43.000Z", "uid": "35240-cf02c590-7ab0-4189-a461-b27020a7e472" } ], "auth": { "type": "bearer", "bearer": [ { "key": "token", "value": "{{bearerToken}}", "type": "string" } ] }, "variable": [ { "key": "baseUrl", "value": "https://api.cerebras.ai" } ] }